English(EN) OpenStamp: A Watermark for Open-Source Language Models

新研究揭示代码水印易受混淆攻击；OpenStamp 提供稳健替代方案

作者 PulseAugur 编辑部 · [3 个来源] · 2026-08-31 04:00

研究人员发现当前AI生成代码的水印方法存在重大漏洞，证明常见的代码混淆技术可以有效消除基于N-gram的水印。另一项研究介绍了OpenStamp，一种专为开源语言模型设计的新水印技术，它将信号直接嵌入模型权重中，使其更能抵抗通过微调或释义进行的移除。 AI

影响新的水印方法对于追踪AI生成内容和确保问责至关重要，但当前技术面临代码混淆和模型可访问性的重大挑战。

排序理由该集群包含两篇学术论文，详细介绍了关于AI生成内容水印技术的新研究。

AI 生成摘要 · Google Gemini · 来自 3 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Research; 该集群包含两篇学术论文，详细介绍了关于AI生成内容水印技术的新研究。
Source corroboration: 3 independent sources; Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics: paper, safety; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: 50 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.
Coverage growth since scoring: +1 source(s) since last score; New sources have picked up this story since our last re-score. Score will update on the next scoring pass.

完整方法见我们的编辑标准。

arXiv cs.AI TIER_1 English(EN) · Jidong Yang, Qi Li, Wei Zong, Yang-Wai Chow, Willy Susilo, Huaike Yu, Chunpeng Wang, Suo Gao · 2026-09-02 04:00

一个提示就够了：通过基础图像模型进行水印清洗

arXiv:2609.01249v1 Announce Type: cross Abstract: Invisible watermarks are typically evaluated against predefined perturbations such as compression, blur, noise, cropping, and denoising. Public foundation image models expose a distinct threat: an attacker can submit a watermarked…
arXiv cs.AI TIER_1 English(EN) · Gehao Zhang, Mingzhe Li, Eugene Bagdasarian, Shiqing Ma, Juan Zhai · 2026-09-01 04:00

消失的墨水：N-gram 代码水印在理论和实践中被混淆技术破解

arXiv:2507.05512v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly used for code generation, making reliable identification of machine-generated code important for attribution, tracking, and misuse detection. Existing code watermarking methods…
arXiv cs.CL TIER_1 English(EN) · Miroojin Bakshi, Saksham Rastogi, Danish Pruthi · 2026-08-31 04:00

OpenStamp：开源语言模型的水印

arXiv:2608.27899v1 Announce Type: new Abstract: With the growing prevalence of large language model (LLM) generated content, watermarking is considered a promising approach for attributing text to LLMs and distinguishing it from human-written content. A prominent class of techniq…